Tweetovi

Blokirali ste korisnika/cu @alucardna

Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @alucardna

  1. Prikvačeni tweet
    12. lis 2019.

    Thank you to everybody who joined my talk! It was a wonderful experience to speak at I'm happy to continue the conversation on multi-lingual hate speech detection, so please get in touch. Here are my slides:

    Prikaži ovu nit
    Poništi
  2. proslijedio/la je Tweet
    31. sij

    Learn more about our first Opt Out Tools meetup with our first Medium Post!

    Poništi
  3. proslijedio/la je Tweet
    27. sij

    Transfer learning is increasingly going multilingual with language-specific BERT models: - 🇩🇪 German BERT - 🇫🇷 CamemBERT , FlauBERT - 🇮🇹 AlBERTo - 🇳🇱 RobBERT

    Prikaži ovu nit
    Poništi
  4. proslijedio/la je Tweet
    26. sij

    Working on a project like Opt Out Tools is rewarding in a multi fold way: its potential massive social impact, the intellectual masturbation, and being with the awesome people around it!

    Poništi
  5. 25. sij

    First time at hosted by and . This fantastic group already has 5 PRs and counting.

    Poništi
  6. proslijedio/la je Tweet
    24. sij

    Last night was our first maintainer meetup! Meet (most of) The Opt Out Tools Team😀 Thank you so much to for being such amazing hosts

    Prikaži ovu nit
    Poništi
  7. proslijedio/la je Tweet
    17. sij

    Are you doing in a non-english language? Try the multilingual XLM-R model! It gave us amazing results in German (for the SOTA chasers: yes, it's also outperforming previous results with BERT & Co). Blog:

    Poništi
  8. proslijedio/la je Tweet
    11. sij

    I published a Finnish language model for : POS tagging and dependency parsing for Finnish on !

    Poništi
  9. proslijedio/la je Tweet
    6. sij

    10 ML & NLP Research Highlights of 2019 New blog post on ten ML and NLP research directions that I found exciting and impactful in 2019.

    Poništi
  10. 30. pro 2019.

    Consequence Scanning Workshop by @optoutsocial in Lecture room M1 starting 12:30 "We will use consequence scanning as a method to think through building tools against online sexual harassment".

    Poništi
  11. proslijedio/la je Tweet
    24. pro 2019.

    me: i wonder what would happen if i trained the neural net gpt-2 on christmas carols? me: ... me: oh NO

    Rudolph the Red Nosed Reindeer, with its red belly
The All-gracious King of all the earth,
Had a baby at Christmas time,
On Christmas Day,
A true and holy Deity,
Went down to earth,
With human flesh for sacrifice.

For sinful men such a Deity doth appear,
And wink and nod in reply,
As he winked and nod in reply,
As he winked and nod in reply

The wretched world is run by ox and ass
The wretched world is run by ox and
    Prikaži ovu nit
    Poništi
  12. proslijedio/la je Tweet
    23. pro 2019.

    New NLP News: 2020 NLP wish lists, HuggingFace + fastai, NeurIPS 2019, GPT-2 things, Machine Learning Interviews via

    Poništi
  13. 20. pro 2019.

    Wondering what it takes to label a hate speech dataset and/or how effective state-of-the-art NLP tools are for different languages? Check out my 2019 talk 🙂

    Poništi
  14. proslijedio/la je Tweet
    1. pro 2019.

    This piece by on AI hype is excellent and I hope it gets broad play: My comments in this thread:

    Prikaži ovu nit
    Poništi
  15. proslijedio/la je Tweet
    17. stu 2019.

    Literally all I do as an NLP engineer: No. No. That's not a clearly defined annotation label. Just try labelling one document. No. Transfer learning still needs labelled data. No. Your corpus is too small for this method. No. Just use a regex. No, regex is still AI. No.

    Poništi
  16. proslijedio/la je Tweet
    15. stu 2019.

    From my upcoming Machine Learning Engineering book. Very few people understand that part or accept it. (The drafts of the first three chapters of the book are available online. The link to the book's website is in the comments.)

    Prikaži ovu nit
    Poništi
  17. 12. stu 2019.

    On the linguistic patterns of "her/hers" and "him/his" which results in data with gender imbalance: “linguistic difference that is not inherently biased could still result in a biased machine learning model.” — Robert Munro

    Poništi
  18. proslijedio/la je Tweet
    9. stu 2019.

    giving a well-deserved shout-out to @optoutsocial at . Check it out and give it a star on GitHub!

    Poništi
  19. 4. stu 2019.

    Great to see a more unified approach to collecting and labeling a multi-lingual hate-speech dataset. The comparable corpora opens the gate for better transfer learning and enables us to more effectively tackle hate-speech online.

    Poništi
  20. proslijedio/la je Tweet
    31. lis 2019.

    🥳 The Transformers library is turning 1⃣ today 🎂 What a ride! - 16k+ stars on Github - 160+ contributors and the most amazing features are still to come, I'm so excited about what's next Here is Megan's humbling shout out to it in her keynote at TensorFlow World yesterday 😍

    , , i još njih 6
    Poništi
  21. 30. lis 2019.

    Great things are happening with OptOut project! Follow the developments and learn all about how to make social media safer and more inclusive.

    Poništi

Čini se da učitavanje traje već neko vrijeme.

Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.

    Možda bi vam se svidjelo i ovo:

    ·